Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 19375
    Prev
    Next
    INDEX
    Explanations

    versions or adaptations of different things

    oai_token-act-pair · gpt-3.5-turbo

    references to different versions of things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iblings
    -0.71
    erity
    -0.70
    urers
    -0.70
    arers
    -0.68
     besides
    -0.67
    nesses
    -0.67
    hya
    -0.62
    ettes
    -0.62
    earchers
    -0.62
    cellaneous
    -0.62
    POSITIVE LOGITS
     sorts
    1.03
     theirs
    0.79
     itself
    0.70
     himself
    0.69
     Yourself
    0.67
     Sleeping
    0.67
     ours
    0.67
     course
    0.66
     themselves
    0.66
     Icar
    0.64
    Activations Density 0.153%

    No Known Activations